Character-based chat and storywriting with large language models: TavernAI is the open-source frontend that leaves model choice to you. It generates no text itself; it connects to the backend of your choice - OpenAI (including GPT-4), Anthropic Claude, KoboldAI and KoboldCpp, Oobabooga's Text Generation Web UI, NovelAI, Ollama, and the crowdsourced Horde - so cost, model quality, and content policy are decided by your backend, not the interface. Characters are defined by portable card files in PNG or JSON format with personality, scenario, and example dialogue, and tens of thousands of community-made cards from sites like Chub.ai import directly. Conversations support group chats with multiple characters, a story mode for long-form writing, message swiping to branch between alternative responses, and full editing of any message. World Info injects lore into context when keywords trigger, keeping long roleplays consistent. Themes, custom backgrounds, and configurable generation settings round out the interface. It runs on Node.js, and the SillyTavern project began as a fork of it.

Open-source alternative to OpenAI's Canvas — a collaborative writing and coding environment where AI agents help you draft, edit, and refine documents through an agentic architecture built on LangGraph. The dual-mode editor combines a BlockNote rich text editor for live-rendered markdown with a CodeMirror-based code editor supporting syntax highlighting across multiple programming languages, letting you switch between prose and code artifacts within the same session. The built-in reflection agent automatically generates style rules and user insights from your chat history, storing them in a shared LangGraph memory store that persists across sessions for increasingly personalized assistance. Pre-built quick actions provide one-click access to common writing transformations including summarize, expand, simplify, and translate, while coding actions offer explain, refactor, add comments, and convert between languages. The monorepo architecture separates the Next.js 14 frontend from the LangGraph agent backend, connecting via HTTP and WebSocket protocols through the @langchain/langgraph-sdk client. Seven LLM providers are supported out of the box — OpenAI, Anthropic Claude, Google Gemini, Fireworks AI, Groq, Azure OpenAI, and local Ollama models — with Supabase handling authentication and data persistence. Deploy via Docker or build from source. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

A private ChatGPT built with Next.js: Lobe Chat is the open-source AI chat interface teams self-host instead. Its main advantage is provider breadth: one interface connects to 40+ model providers, including OpenAI, Anthropic Claude, Google Gemini, Mistral, Groq, AWS Bedrock, Azure, and local models served through Ollama, so you can switch models per conversation and compare outputs. It handles multi-modal work: image recognition, image generation, text-to-speech, and speech-to-text. A plugin system based on function calling and the Model Context Protocol (MCP) adds external tools like web search and code execution. Run it in standalone mode as a single container with settings in browser storage, or in database mode with PostgreSQL and S3-compatible storage for persistent history, multi-user auth, and RAG knowledge bases built from uploaded documents with pgvector retrieval. Because tools arrive through function calling and MCP rather than a proprietary plugin format, custom internal tools can be exposed to the assistant with a standard server over STDIO or HTTP. Hundreds of pre-configured assistant roles import from the community marketplace. For teams the cost model matters: provider API keys billed per token typically undercut a ChatGPT Plus seat per person, and self-hosting keeps API keys, uploaded files, embeddings, and conversation history entirely on your own server.

Large language models get a polished front end that can run fully offline: Open WebUI is the self-hosted front end of choice. It talks to local model runners, primarily Ollama, and to any OpenAI-compatible API, so LM Studio, vLLM, Groq, Mistral, OpenRouter, and cloud providers all plug into the same chat interface and can be mixed per conversation. RAG is built in: upload files to knowledge bases or reference them in chat with the # command, backed by a choice of nine vector databases (ChromaDB and PGVector officially maintained) and multiple extraction engines including Tika and Docling, with hybrid BM25-plus-vector search and cross-encoder reranking. Web search results from providers like SearXNG, Brave, and Tavily inject directly into conversations. Extensibility comes from Python tools and functions that run inside the chat, a Pipelines plugin framework, and native MCP support. Multi-user features include RBAC, SSO, and group permissions, and the instance itself exposes an OpenAI-compatible API your own apps can call.

Every major model provider behind one ChatGPT-style interface: LibreChat spans OpenAI, Anthropic, Google, Azure, AWS Bedrock, Vertex AI, Groq, Mistral, OpenRouter, DeepSeek, and any OpenAI-compatible endpoint including local Ollama. You can switch models mid-conversation and compare providers without changing tools. Its Agents framework builds no-code custom assistants with tool access via Model Context Protocol servers, file search over uploaded documents through an optional pgvector-backed RAG service, and a sandboxed Code Interpreter that executes Python, JavaScript, Go, C++, Java, PHP, and Rust. Artifacts render React components, HTML, and Mermaid diagrams directly in chat, and image generation works through DALL-E and other configured providers. Multi-user support is enterprise-grade, with OAuth, SAML, LDAP, and two-factor authentication, per-user conversation history in MongoDB, and Meilisearch-powered search across all messages and files, plus reusable presets, forkable threads, and persistent memory across conversations. The economics favor teams: instead of a ChatGPT Plus seat per person, everyone shares one instance billed per API token, with access to every provider rather than one - and providers see individual API calls, not your accumulated organizational knowledge. Deployment is Docker Compose; API keys and endpoints are configured through .env and librechat.yaml.

Self-hosting a language model is only half the job; people still need somewhere pleasant to talk to it, and Chat UI is that window, the same interface that powers HuggingChat. Point it at any OpenAI-compatible endpoint, your own Ollama or llama.cpp server, the Hugging Face router, or a hosted gateway like OpenRouter, and the models it serves appear in the picker automatically, with no per-model configuration. Conversations are saved to your database and stay browsable in the sidebar, so a thread from last week can be reopened, continued, and compared against a fresh answer from another model. Multimodal models accept image uploads right in the composer, and models that support it can call MCP tools mid-conversation to fetch data or run actions. For a shared team deployment, OpenID Connect sign-in keeps individual histories and settings separate, and per-user defaults travel with each account. Everything a consumer chatbot would keep on someone else's servers, prompts, uploaded files, and usage history, stays in the MongoDB you control on the same machine. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Grammar, punctuation, and style errors a dictionary lookup can't see: LanguageTool is open-source proofreading powered by a Java rule engine covering English, German, Spanish, French, Portuguese, Dutch, and 25+ other languages. Self-hosting the HTTP server is how you get Grammarly-class checking without sending every sentence you write to a third party - a real concern when the text being proofread is confidential email, legal drafts, or unreleased documentation. Your instance exposes the standard /v2/check API, so the official ecosystem plugs straight in: browser extensions for Chrome and Firefox accept a custom server URL, and integrations exist for VS Code, LibreOffice, Obsidian, Vim, Emacs, and many editors. Notably, self-hosting restores free browser-extension checking that the hosted service moved behind a premium subscription - your server, no character limits, no paywall. Detection quality is tunable: optional n-gram datasets (multi-gigabyte language models for en, de, es, fr, nl) teach the engine word-order and confusion-pair errors like there/their and brakes/breaks, and a fastText model improves automatic language identification. Everything runs offline once models are downloaded. The core is LGPL, the API is documented with Swagger, and rules are community- maintained and constantly expanding.

A web interface for a folder of Markdown files - Flatnotes is exactly that, and the discipline of that design is why people love it. Every note is a plain .md file in a single flat directory: no database, no proprietary format, no hierarchy to maintain, no export step if you ever leave. Edit notes in the browser or open the same files in VS Code or Obsidian, sync them with Syncthing or rsync while the app is running - the Whoosh-powered search index synchronizes incrementally, so external edits just show up. The interface is a clean Vue.js app with both WYSIWYG and raw Markdown editing modes (TOAST UI Editor), instant full-text search behind the "/" shortcut with partial-match support, wikilinks for cross-note references, and automatic tag extraction from #hashtags in note bodies. Light and dark themes and a mobile-responsive layout make it pleasant everywhere. Authentication is flexible for a personal tool: none, read-only, username/password, or TOTP two-factor. A documented REST API covers create/read/update/delete for automation. The operational story is the quiet selling point - the only state is the notes folder and a rebuildable index, so backup is copying a directory. For a personal notepad that respects your data, Flatnotes nails minimal.

In continuous open-source development since 2009, Etherpad is the original really-real-time collaborative editor - used by Wikimedia, governments, EU public-sector institutions, and tens of thousands of self-hosters. Its core idea is visible authorship: every keystroke is attributed with author colors, every revision preserved, and the timeslider lets you scrub through a document's entire history character by character. Multiple people type into the same pad and see each other's changes instantly - it scales to thousands of simultaneous editors per pad. The base install is deliberately lightweight; capability comes from roughly 290 plugins installable from the admin web UI: comments, images, tables, drawing, video chat via WebRTC, math rendering, code highlighting, and authentication via OAuth, LDAP, or OpenID. AI is pointedly a plugin, not a default - you choose the model and infrastructure, or never turn it on. There is no telemetry. For integrators, an HTTP API (with OpenAPI definitions at /api/openapi.json) manages pads, users, and groups for embedding in your own applications, and the ueberDB abstraction layer supports PostgreSQL, MySQL, Redis, MongoDB, and SQLite backends. Full data export is built in, the format is open, it is translated into 105 languages, and it runs on anything from a Raspberry Pi to a server farm. Apache 2.0 licensed, Node.js based.

Get ready to transform your audience into a thriving empire with Ghost, the ultimate toolkit for the modern creator on a mission to monetize their mojo. Picture this: a sleek website that screams 'you', bursting with content that captivates, newsletters that fly straight into inboxes, and a subscription service that turns followers into financiers. Wave goodbye to bland and hello to a smorgasbord of stunning, free themes that you can finesse to fit your unique flair. But wait, there's more! Ghost's editor is like the Swiss Army knife for content connoisseurs—slick, sophisticated, and oh-so-simple to use. Unleash your creativity with multimedia storytelling that includes everything but the kitchen sink—galleries, chucklesome gifs, videos, podcasts, you name it. And when it's time to hit 'send', those built-in newsletters make sure your words woo your audience without breaking a sweat. Want to play the mysterious type? Ghost's got you covered with native signup forms that turn casual lurkers into committed members. And because we all love a good sneak peek, Ghost dishes out the deets with analytics that spill the tea on who's loving your work the most. Plus, with tantalizing offers and promotions, you'll have new subscribers flocking like seagulls at a beach picnic. All this, hosted on RepoCloud, where the cost is as tiny as your chances of being bored. So, what are you waiting for? Let's Ghost!

With over 5,100 GitHub stars and a proven track record powering more than 550,000 blogs on the Write.as hosted platform since 2018, WriteFreely strips blogging down to its essential purpose — writing — by removing news feeds, notifications, likes, and engagement metrics that distract from the creative process. The Go binary deploys on any platform as a single executable with SQLite for zero-dependency setups or MySQL and MariaDB for larger installations, consuming minimal system resources and running comfortably on hardware as small as a Raspberry Pi. The auto-saving Markdown editor provides a clean writing environment with instant draft preservation, while published posts render with typography-focused CSS that puts content front and center for readers. ActivityPub federation connects every blog to the fediverse, allowing Mastodon, Pleroma, and other ActivityPub platform users to follow blogs directly, receive new posts in their timelines, and boost or favorite content to their followers. Multi-blog support lets writers maintain separate blogs with distinct pen names from a single account without revealing their association, while OAuth 2.0 integration enables single sign-on onboarding from existing identity providers. Hashtag categorization organizes posts by topic, pinned posts create static pages for permanent content, and draft mode lets writers compose privately before publishing. Blog elements are localized in over 20 languages with first-class right-to-left script support for Arabic, Hebrew, and other RTL languages. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

The most feature-complete open-source alternative to Google's NotebookLM — a self-hosted research platform where you upload PDFs, videos, audio files, and web pages into organized notebooks, then chat with your content, generate multi-speaker podcasts, and run semantic search across everything without sending a single byte to Google's servers. The podcast engine supports 1-4 fully customizable speakers with backstories, personalities, and expertise profiles, generating professional audio dialogue through OpenAI, ElevenLabs, Google TTS, or completely local text-to-speech via Kokoro for maximum privacy. Content processing uses token-based chunking with RAG-powered retrieval grounded in your uploaded sources, while both full-text keyword search and semantic vector search via SurrealDB enable conceptual discovery across all notebooks. The 18+ supported AI providers include OpenAI, Anthropic, Google Gemini, Groq, Ollama, LM Studio, and more — configurable per task so you can route cheap models to summarization and powerful models to analysis. Content transformations extract insights, generate summaries, create study guides, and produce structured outputs from any source material. The MCP integration connects Open Notebook to Claude Desktop, VS Code, and other MCP clients for seamless workflow integration. A full REST API on port 5055 enables complete automation of notebook management, source upload, and podcast generation. Deploy via Docker Compose with the application container, SurrealDB v2 on RocksDB, and optional TTS containers. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

DramaClaw is a self-hosted production line that carries a manuscript or screenplay all the way to a finished AI drama, handling story structure, characters, storyboards, voices, and final cuts inside one workspace. Drop in a novel manuscript or a Fountain screenplay and it builds episodes, characters, and scenes for you, then plans multi-episode arcs and writes scripts in adaptive, literal, or staged modes with review-and-repair loops. The shared asset library keeps every character, scene, prop, and voice organized once, so faces stay consistent across episodes while portraits and per-episode variants handle costume and age changes. Storyboards and first frames are generated beat by beat, emotion-aware voice-over is synthesized per character, and episodes are assembled and exported with subtitles and the full asset pack. For finer control, the XiaHua canvas gives you 18 node types for images, video, audio, scripts, and 3D sets, with a wall of 45 short-drama styles and tools for relighting, outpainting, upscaling, and camera moves. Xia Director, the built-in agent, turns a plain-language brief into a node graph, runs it with progress tracking, and can promote winning results from the canvas back into the series. You pick the models: paste an official gateway key, or route Seedance, Kling, Hailuo, Sora, ComfyUI, and other channels through the bundled gateway, while external agents drive the same pipeline over MCP. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Elastic License 2.0 licensed.